x-research

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to use the "web_search" and "x_search" tools and shows curl examples that fetch and summarize public web pages and X/Twitter posts, meaning the agent ingests untrusted, user-generated third‑party content (web pages and social media) as part of its workflow and can let that content influence its outputs/actions.